Prompting Large Language Models to adopt specific social identities can reduce bias, as demonstrated by Dong et al. (2024a), and mirror human-like ingroup favoritism, as demonstrated by Hu et al. (2025a).

Authors

• Person: Not available Organization: arXiv
  A Survey of Incorporating Psychological Theories in LLMs - arXiv

Sources

• A Survey of Incorporating Psychological Theories in LLMs - arXiv arxiv.org arXiv via serper

Referenced by nodes (2)

• Large Language Models concept
• bias concept